Stop AI from lying about your code.
The local CLI that forces AI agents to prove their file edits against your actual filesystem. Zero slop. Full verification.
$ npx mythos-router chatCopiedCA: 0xb942b75a602fa318ac091370d93d9143ba345ba3CopiedChoose the path that matches your setup
Start with the path you actually need. Mythos can run the agent, load repo rules, or act as the verified file-edit boundary for another agent.
Run one task or open chat
For developers who want Mythos to call a configured provider and verify any file edits it makes.
mythos initmythos run "explain this repo"Generate and load skills
For teams that want repo rules, review expectations, and risk surfaces available every session.
mythos learnmythos run --file TASK.md -s repoUse Mythos over MCP
For MCP clients or external agents that need local dry-runs, verified applies, rollback, receipts, and skill inspection.
mythos mcpswd_dry_run / swd_applyThe part worth showing is the proof layer.
Mythos does not ask you to trust a model's story. It treats each file edit as a claim, compares it with the real filesystem, and records what actually happened.
A normal edit finishes with filesystem proof.
The model proposes file actions, SWD checks the actual disk state, and the run only completes after the edit matches the claim.
Static playback using the current CLI output shape.
Built for verifiable agent work
Mythos Router is not another chat wrapper. It is a local execution boundary for model output, repo rules, receipts, MCP clients, and external-agent file actions.
Strict Write Discipline
Every claimed file edit is checked against the real filesystem with before and after snapshots, hashes, and verification status.
MCP adapter for SWD
MCP clients can use mythos mcp as a local tool server for dry-runs, verified applies, receipts, and skill inspection.
One-shot run mode
Use mythos run for scriptable one-off tasks from inline prompts, files, or stdin while keeping the same SWD, memory, budget, skills, and receipt path.
Repo skills
Keep project rules in .mythos/skills/<name>/SKILL.md or personal reusable rules in ~/.mythos-router/skills. Active skills are recorded in receipts.
Repo learning
mythos learn creates a reviewable repo-local SKILL.md from local project signals without running npm scripts, tests, builds, or model calls.
Receipts and drift checks
Verified runs write local receipts with file hashes, provider or external-agent metadata, git context, rollback status, and later drift verification.
One verified path for agent writes
Mythos can be the agent interface or just the execution layer. The trust model stays the same either way.
Model or agent proposes actions
Use Mythos chat/run, or bring your own external agent through mythos mcp or mythos swd apply.
Mythos validates the boundary
Input is parsed, paths are constrained to the project, sensitive files are blocked, and high-impact actions require explicit opt-in.
SWD applies and verifies
The engine snapshots disk state, applies approved changes, verifies the actual filesystem, and rolls back failed writes.
Receipts keep the record
Successful non-dry-run writes produce local receipts with file hashes, provider, MCP, or external-agent metadata, git context, and drift checks.
Copy the command you need
Install Mythos locally, then run the command for your flow. Chat and run need a provider key; MCP and external-agent SWD can verify submitted file actions without a Mythos model call.
$ npm install -g mythos-router$ mythos chat$ mythos run --file TASK.md$ mythos mcp$ mythos init --check$MYTHOS
The native token for the mythos-router ecosystem on Base. API billing integrations and token-gated features are on the roadmap — building the core engine first.
0xb942b75a602fa318ac091370d93d9143ba345ba3